{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E62WPXFIQZGLZIHPB4LRMFX5M6","short_pith_number":"pith:E62WPXFI","canonical_record":{"source":{"id":"2311.14028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T14:33:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3193e40a2189164231cd38aef0b744795f4919e81524b18d6c346916ec473752","abstract_canon_sha256":"7daa1735c80f2e807cc3924c7e03ccf93c930beb76e01806ef9fe57f06dde8e8"},"schema_version":"1.0"},"canonical_sha256":"27b567dca8864cbca0ef0f171616fd679146ebf00811458d631555394d530700","source":{"kind":"arxiv","id":"2311.14028","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14028","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14028v2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14028","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"E62WPXFIQZGL","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"E62WPXFIQZGLZIHP","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"E62WPXFI","created_at":"2026-07-05T10:23:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E62WPXFIQZGLZIHPB4LRMFX5M6","target":"record","payload":{"canonical_record":{"source":{"id":"2311.14028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T14:33:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3193e40a2189164231cd38aef0b744795f4919e81524b18d6c346916ec473752","abstract_canon_sha256":"7daa1735c80f2e807cc3924c7e03ccf93c930beb76e01806ef9fe57f06dde8e8"},"schema_version":"1.0"},"canonical_sha256":"27b567dca8864cbca0ef0f171616fd679146ebf00811458d631555394d530700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:18.018567Z","signature_b64":"YiT/k1pPYvz96yQO/Z1QAZGI3aAQ/EbfxYGZlyPXATQeYj1XxM3NcY7mSpkkwpiOh1m2/Pp/OD++42Wm72aWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27b567dca8864cbca0ef0f171616fd679146ebf00811458d631555394d530700","last_reissued_at":"2026-07-05T10:23:18.018005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:18.018005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.14028","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xaRW+c5bH2XqzkQFWz/jOtA2MfsNzKyHC+HzYQtRNEddokEAix7vZQaQ75UEmJeiCR/2vVltX098D+jw6MqkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:26:28.647335Z"},"content_sha256":"cdb41192742e3aeaed69d583b55a6d359a03a4179605303467761e3692d67b74","schema_version":"1.0","event_id":"sha256:cdb41192742e3aeaed69d583b55a6d359a03a4179605303467761e3692d67b74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E62WPXFIQZGLZIHPB4LRMFX5M6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Learning of Diffusion Models with Generative Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Gido M. van de Ven, Pau Rodriguez, Sergi Masip, Tinne Tuytelaars","submitted_at":"2023-11-23T14:33:03Z","abstract_excerpt":"Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for incrementally learning new tasks and accumulating knowledge, thus enabling the reuse of trained models for further learning. One potentially suitable continual learning approach is generative replay, where a copy of a generative model trained on previous tasks produces synthetic data that are interleaved with data from the current task. However, standard generative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14028","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.14028/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcJwpN/rIbSwzG+tnYBpOA4w3tbUS+LwwaLyD6LY34enXNQQ9uUCCaPVYrMTx3/Rn3z63ZgHUqZneBDJn23WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:26:28.647847Z"},"content_sha256":"21cb8b893d73066985633e4f719d74172931885e83b34654182bfe54f3cb1923","schema_version":"1.0","event_id":"sha256:21cb8b893d73066985633e4f719d74172931885e83b34654182bfe54f3cb1923"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/bundle.json","state_url":"https://pith.science/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T06:26:28Z","links":{"resolver":"https://pith.science/pith/E62WPXFIQZGLZIHPB4LRMFX5M6","bundle":"https://pith.science/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/bundle.json","state":"https://pith.science/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E62WPXFIQZGLZIHPB4LRMFX5M6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E62WPXFIQZGLZIHPB4LRMFX5M6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7daa1735c80f2e807cc3924c7e03ccf93c930beb76e01806ef9fe57f06dde8e8","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T14:33:03Z","title_canon_sha256":"3193e40a2189164231cd38aef0b744795f4919e81524b18d6c346916ec473752"},"schema_version":"1.0","source":{"id":"2311.14028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14028","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14028v2","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14028","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"E62WPXFIQZGL","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"E62WPXFIQZGLZIHP","created_at":"2026-07-05T10:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"E62WPXFI","created_at":"2026-07-05T10:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:21cb8b893d73066985633e4f719d74172931885e83b34654182bfe54f3cb1923","target":"graph","created_at":"2026-07-05T10:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.14028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for incrementally learning new tasks and accumulating knowledge, thus enabling the reuse of trained models for further learning. One potentially suitable continual learning approach is generative replay, where a copy of a generative model trained on previous tasks produces synthetic data that are interleaved with data from the current task. However, standard generative","authors_text":"Gido M. van de Ven, Pau Rodriguez, Sergi Masip, Tinne Tuytelaars","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T14:33:03Z","title":"Continual Learning of Diffusion Models with Generative Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14028","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cdb41192742e3aeaed69d583b55a6d359a03a4179605303467761e3692d67b74","target":"record","created_at":"2026-07-05T10:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7daa1735c80f2e807cc3924c7e03ccf93c930beb76e01806ef9fe57f06dde8e8","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T14:33:03Z","title_canon_sha256":"3193e40a2189164231cd38aef0b744795f4919e81524b18d6c346916ec473752"},"schema_version":"1.0","source":{"id":"2311.14028","kind":"arxiv","version":2}},"canonical_sha256":"27b567dca8864cbca0ef0f171616fd679146ebf00811458d631555394d530700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27b567dca8864cbca0ef0f171616fd679146ebf00811458d631555394d530700","first_computed_at":"2026-07-05T10:23:18.018005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:18.018005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YiT/k1pPYvz96yQO/Z1QAZGI3aAQ/EbfxYGZlyPXATQeYj1XxM3NcY7mSpkkwpiOh1m2/Pp/OD++42Wm72aWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:18.018567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdb41192742e3aeaed69d583b55a6d359a03a4179605303467761e3692d67b74","sha256:21cb8b893d73066985633e4f719d74172931885e83b34654182bfe54f3cb1923"],"state_sha256":"9b54327457a3794e6817125672258e5a7a812979eca5409f5d990e824919513b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a31jdoRflI5J5C6DpCvI2VVk1YX8O27t1Ul17GL8jW/CK/IdtRlgAjlyPFXzKlgAlhnGy+OWH7AGsxstzsD6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:26:28.652607Z","bundle_sha256":"5573c688810815df8bab5fffcdecb2c1b4b9036502c233fa720429e8e3ac13f6"}}